浅析php插件 HTMLPurifier HTML解析器

<?php
require_once 'HTMLPurifier.auto.php';
$config = HTMLPurifier_Config::createDefault();
?>

<?php
require_once 'HTMLPurifier.includes.php';
require_once 'HTMLPurifier.autoload.php';
$config = HTMLPurifier_Config::createDefault();
?>

require_once 'HTMLPurifier.auto.php';

require_once 'HTMLPurifier.includes.php';
require_once 'HTMLPurifier.autoload.php';

$config->set('HTML.AllowedElements', array('div'=>true, 'table'=>true, 'tr'=>true, 'td'=>true, 'br'=>true));
$config->set('HTML.Doctype', 'XHTML 1.0 Transitional')  //html文档类型（常设）
$config->set('Core.Encoding', 'UTF-8')   //字符编码（常设）

$purifier = new HTMLPurifier($config);

$puri_html = $purifier->purify($html);

<?php
require_once 'HTMLPurifier.includes.php';
require_once 'HTMLPurifier.autoload.php';
class Resume_HtmlPurifier implements Zend_Filter_Interface{
 protected $_htmlPurifier = null;
 public function __construct($options = null)
 {
  $config = HTMLPurifier_Config::createDefault();
  $config->set('Code.Encoding', 'UTF-8'); 
  $config->set('HTML.Doctype', 'XHTML 1.0 Transitional')
  if(!is_null($options)){
   foreach($options as $option){
    $config->set($option[0], $option[1], $option[2]);
   }
  }
  $this->_htmlPurifier = new HTMLPurifier($config);
 }
 public function filter($value)
 {
 return $this->_htmlPurifier->purify($value);

 }
}
?>

$conf = array(
 array('HTML.AllowedElements',
           array(
                     'div' => true,
                     'table' => true,
                     'tr' => true,
                     'td' => true,
                     'br' => true,
                 ),
                 false), //允许属性 div table tr td br元素
         array('HTML.AllowedAttributes', array('class' => TRUE), false),  //允许属性 class
         array('Attr.ForbiddenClasses', array('resume_p' => TRUE), false), //禁止classes如
         array('AutoFormat.RemoveEmpty', true, false),    //去空格
         array('AutoFormat.RemoveEmpty.RemoveNbsp', true, false),  //去nbsp
         array('URI.Disable', true, false),
);

$p = new Resume_HtmlPurifier($conf);
$puri_html = $p->filter($html);